Title :
Higher-order statistics in object recognition
Author :
Breuel, Thomas M.
Author_Institution :
IDIAP, Lausanne, Switzerland
Abstract :
A higher-order statistical theory of matching models against images is developed. The basic idea is to take into account how much of an object can be seen in the image, and what parts of it are jointly present. It is shown that this additional information can improve the specificity (i.e., reduce the probability of false positive matches) of a recognition algorithm. Higher-order statistics are derived from a physical world model and the minimum description length principle. Statistical information is used in a top-down way for the evaluation (verification) of specific model and pose hypotheses
Keywords :
image matching; image recognition; object recognition; probability; statistics; false positive matches; higher-order statistical theory; minimum description length principle; models matching; object recognition; physical world model; pose hypotheses; probability; Bayesian methods; Higher order statistics; Image recognition; Layout; Milling machines; Object recognition; Probability; Shape; Solid modeling; Tail;
Conference_Titel :
Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93., 1993 IEEE Computer Society Conference on
Conference_Location :
New York, NY
Print_ISBN :
0-8186-3880-X
DOI :
10.1109/CVPR.1993.341018
